INDEX

Explanations

technical terms related to computer security

oai_token-act-pair · gpt-3.5-turbo

terms related to specific locations or contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStream

-0.77

kid

-0.75

pid

-0.74

alus

-0.73

quet

-0.72

natureconservancy

-0.70

REDACTED

-0.70

otos

-0.67

achu

-0.67

uca

-0.67

POSITIVE LOGITS

theless

0.81

 transmission

0.72

 garbage

0.71

 equivalents

0.70

 versions

0.68

omn

0.67

 productions

0.67

 mode

0.67

 operation

0.67

 auto

0.65

Activations Density 0.147%

technical terms related to computer security

terms related to specific locations or contexts

No Comments

No Known Activations